Prompt Engineering：如何让大模型按要求“工作”
"链式思考" 相关文章
MONA: Three Month Later - Updates and Steganography Without Optimization Pressure
Reasoning models don't always say what they think
What faithfulness metrics should general claims about CoT faithfulness be based upon?
Anthropic’s Evaluation of Chain-of-Thought Faithfulness: Investigating Hidden Reasoning, Reward Hacks, and the Limitations of Verbal AI Transparency in Reasoning Models
How Do LLMs Reason? 5 Approaches Powering the Next Generation of AI
The Most Forbidden Technique
Worries about latent reasoning in LLMs
Implications of the inference scaling paradigm for AI safety
InternVL 2.5，首个MMMU超过70%的开源模型，性能媲美GPT-4o
